Information processing device, information processing method, and information processing program

Abstract

To promote the soundness of a comment field.SOLUTION: An information processing device comprises a determination unit, a selection unit, and an inquiry unit. The determination unit determines whether a contributor of a comment to a content is a party of the content on the basis of account information of the contributor. When the determination unit determines that the contributor is the party related to the content, the selection unit selects a verified account related to the content. The inquiry unit inquires of the verified account selected by the selection unit whether the contributor is the person himself / herself.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] BACKGROUND ART Conventionally, there is known a technique for providing comments posted by other users to a user viewing distributed content such as a news article (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-197422 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology leaves room for improvement in terms of maintaining a healthy comment section. Specifically, the conventional technology does not take into consideration how to prevent impersonation by comment posters.

[0005] The present invention has been made in view of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can improve the health of comment sections. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, an information processing device according to the present invention includes a determination unit, a selection unit, and an inquiry unit. The determination unit determines whether a poster of a comment on content is a party to the content based on the poster's account information. The selection unit selects an authenticated account associated with the content when the determination unit determines that the poster is a party to the content. The inquiry unit inquires of the authenticated account selected by the selection unit about whether the poster is the person in question. [Effects of the Invention]

[0007] According to the present invention, it is possible to improve the health of comment sections. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of information stored in the content information storage unit according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in an account information storage unit according to the embodiment. [Figure 5] FIG. 5 is a schematic diagram of a pronto according to an embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 7] FIG. 7 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing method is executed by, for example, an information processing device 1 shown in Fig. 1.

[0011] 1 is an information processing device that provides various services to a user U via the Internet. In the present disclosure, the information processing device 1 provides various services related to news sites to the user U. Note that the information processing device 1 is realized by, for example, a server device, a cloud system, or the like.

[0012] The user terminal 50 is a terminal device owned by the user U, and acquires various information from the information processing device 1 through data communication with the information processing device 1. In the present disclosure, the user terminal 50 provides news articles distributed from the information processing device 1 to the user U. Examples of the user terminal 50 include a smartphone, a tablet terminal, a personal computer, and a wearable terminal.

[0013] Meanwhile, some news sites offer services that accept comments on news articles from users U and provide the comments attached to the news articles. In such services, comments posted in the comment section of a news article can also be considered as part of the content.

[0014] On the other hand, it is conceivable that, for example, user U may post a comment pretending to be a person involved in a news article. Posting such a comment by impersonating another person is an obstacle to maintaining a healthy comment section.

[0015] Therefore, the information processing device 1 according to the embodiment performs a process of determining whether a comment has been made by an impersonator, and refrains from publishing any impersonated comments. Specifically, as shown in Fig. 1, the information processing device 1 first distributes distribution content to the user terminal 50 (step S1). The distribution content includes news articles and comments posted for each news article.

[0016] Next, the information processing device 1 accepts a comment posted by the user U through the user terminal 50 (step S2). At this time, the information processing device 1 accepts a comment on the news article provided to the user U through the user terminal 50.

[0017] Next, the information processing device 1 executes a determination process (step S3). The determination process here is a process of determining whether the poster of the comment is a party to the news article. Here, a party refers to a person mentioned in the news article, their associates, or a person belonging to an organization mentioned in the news article. In this disclosure, the party refers to a celebrity, a public figure, etc.

[0018] The information processing device 1 executes a determination process based on the poster's account information and the content of the news article. For example, if the poster's account name appears in the news article, the information processing device 1 determines that the poster of the comment is a party to the news article.

[0019] More specifically, the information processing device 1 determines that the poster of a comment is a party to the news article if the poster's account is not an authenticated account, the account was opened within a specified date and time, and the poster's account name appears in the news article.

[0020] That is, if the poster's account information satisfies these conditions, the information processing device 1 determines that the poster may be an impersonator. Then, when the information processing device 1 determines that the poster of the comment is a party to the news article, it executes a selection process (step S4).

[0021] Here, the selection process is a process of selecting a contact point for inquiring whether the poster is the person in question. In the present disclosure, the information processing device 1 selects an authenticated account related to the news article as the contact point.

[0022] Specifically, for example, if the news article is about economics, the information processing device 1 selects an account of an economics expert from among the authenticated accounts. In other words, the information processing device 1 matches the news article on which the poster posted a comment with an expert who is knowledgeable in the field of the news article. Note that the information processing device 1 may select an authenticated account to contact for inquiries, taking into consideration the content of the comment. In this case, the information processing device 1 selects multiple authenticated accounts.

[0023] Next, the information processing device 1 performs an inquiry process to inquire of the selected authenticated account Ua (step S5). For example, the information processing device 1 inquires of the selected authenticated account Ua about the content posted by the poster and whether the poster's account is trustworthy.

[0024] Thereafter, the information processing device 1 acquires a response to the inquiry from the authenticated account Ua (step S6), and performs a decision process (step S7). Here, the decision process is a process for deciding whether to make the comment public or private.

[0025] As will be described later, the response from the authenticated account includes the content of the poster's post, the result of a determination as to whether the poster's account is trustworthy, and the basis for that determination. Then, the information processing device 1 determines whether to make the comment public or private based on the response obtained from each authenticated account.

[0026] Specifically, the information processing device 1 determines whether to make a comment public or private using a sentence generation model trained to generate answers to input sentences in natural language. More specifically, in the determination process, the information processing device 1 first generates a prompt that includes the answers acquired from each authenticated account Ua and an instruction sentence for determining whether the poster is the person in question.

[0027] Next, the information processing device 1 inputs the generated prompt into a sentence generation model and obtains an answer to the prompt from the sentence generation model. At this time, if the information processing device 1 determines, based on the answer from the sentence generation model, that the poster is the actual person involved, it decides to make the comment public. Furthermore, if the information processing device 1 determines, based on the answer from the sentence generation model, that the poster is not the actual person involved, that is, if it determines that the poster is likely to be an impersonator, it decides to make the comment private. Note that the information processing device 1 may also decide to make the comment private if it cannot determine, based on the answer from the sentence generation model, whether the poster is the actual person involved.

[0028] In this way, when the information processing device 1 determines that the poster of the comment is a party to the news article, it makes an inquiry to the authenticated account related to the news article and determines whether to make the comment public based on the result. Therefore, the information processing device 1 according to the embodiment can prevent comments posted by impersonators, thereby improving the health of the comment section.

[0029] [2. Configuration example of information processing device] Next, a configuration example of the information processing device 1 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing device 1 according to an embodiment. As shown in Fig. 2, the information processing device 1 has a communication unit 2, a storage unit 3, and a control unit 4.

[0030] The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 transmits and receives information to and from an external device via a network such as various wireless communication networks, such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0031] The storage unit 3 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 also has a content information storage unit 31, an account information storage unit 32, and a sentence generation model storage unit 33.

[0032] The content information storage unit 31 stores content information. Fig. 3 is a diagram showing an example of information stored in the content information storage unit 31 according to the embodiment. As shown in Fig. 3, the content information storage unit 31 stores information on items such as "content ID," "category," "content data," and "comments" in association with each other.

[0033] The "Content ID" field stores an identifier for identifying each piece of content (news article). The "Category" field stores the category of the content (news article) identified by the corresponding content ID. The category may indicate the field of the corresponding content, such as "Economy," "Entertainment," or "Sports," or may indicate the topic of the content.

[0034] The "content data" item stores content data identified by the corresponding content ID. The content data is data related to news articles, and includes the title, thumbnail image, main text, summary, etc. of the news article.

[0035] The "Comment" field stores comments posted to the content identified by the corresponding content ID. The comments are those posted on news sites, but also include comments posted when posting news articles on social media.

[0036] Returning to the explanation of Fig. 2, the account information storage unit 32 will be explained. The account information storage unit 32 stores account information. The account information is information relating to the account of each user U.

[0037] Fig. 4 is a diagram showing an example of information stored in the account information storage unit 32 according to the embodiment. As shown in Fig. 5, the account information storage unit 32 stores information on items such as "account ID," "registration information," "authenticated flag," and "genre" in association with each other.

[0038] The "account ID" item stores the account ID. The account ID is an identifier for identifying each user U. The "registration information" item stores the registration information. The registration information is information that the user U identified by the corresponding account ID has registered on a news site provided by the information processing device 1.

[0039] The registration information includes information on demographic attributes such as name, age, address, and occupation, as well as information on psychographic attributes such as hobbies and preferences. The registration information may also include information registered by the user U on other services affiliated with the news site. The other services may include various e-commerce sites such as shopping sites and flea market sites, reservation sites for restaurants, hotels, and flights, and electronic payment services that offer credit card and QR code (registered trademark) payments.

[0040] The "authenticated flag" field stores an authenticated flag that indicates whether the account identified by the corresponding account ID has been authenticated. For example, the authenticated flag of an authenticated account is "1," and the authenticated flag of an unauthenticated account is "0."

[0041] The "authenticated flag" may be a flag indicating whether the user U of the account identified by the corresponding account ID has been authenticated and is an expert or knowledgeable person in a particular field. In this case, an account with an authenticated flag of "1" indicates that the user U has been authenticated and is an expert or knowledgeable person in a particular field.

[0042] The "genre" item stores information about the genre of the user U identified by the corresponding account ID. For example, if the corresponding user U is an expert, information about the field of expertise is stored as "genre" in the "genre" item. Note that "genre" is assigned to authenticated accounts that have been approved in advance by the news site as experts (knowledgeable persons).

[0043] Returning to the explanation of FIG. 2, the sentence generation model storage unit 33 will be explained. The sentence generation model storage unit 33 stores a sentence generation model. The sentence generation model is a large-scale language model trained to generate a response sentence to an input natural language sentence. For example, the sentence generation model is a GPT (Generative Pre-trained Transformer).

[0044] Next, we will explain the control unit 4. The control unit 4 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, executing various programs stored in a storage device inside the information processing device 1 using RAM as a working area.

[0045] As shown in FIG. 2, the control unit 4 includes a distribution unit 41, a reception unit 42, a determination unit 43, a selection unit 44, an inquiry unit 45, and a determination unit 46.

[0046] The distribution unit 41 distributes distribution content to each user terminal 50. For example, the distribution unit 41 distributes news articles and comments posted to the news articles as distribution content.

[0047] Specifically, the distribution unit 41 distributes information about the top page of the news site to each user terminal 50, and then distributes distribution content corresponding to the news article selected by the user U.

[0048] The reception unit 42 receives comments on news articles from users U. For example, the reception unit 42 registers the received comments in the “comments” field of the content information storage unit 31 by linking them with the user ID of the user U who posted the comments.

[0049] The determination unit 43 determines whether a poster of a comment on content is a party to the content based on the poster's account information. For example, when the poster's account information satisfies a predetermined condition, the determination unit 43 determines whether the poster of the comment is a party to the content.

[0050] For example, the judgment unit 43 judges that the poster of a comment is a party to the news article if the poster's account name appears in the news article, the poster's account is not an authenticated account, and the account was opened within a specified date and time.

[0051] The determination by the determination unit 43 may be rule-based, or may be performed using, for example, a sentence generation model. For example, when performing the determination using a sentence generation model, the determination unit 43 generates a prompt including the news article, the poster's comment, the poster's account information, and an instruction sentence, and inputs the prompt to the sentence generation model. For example, the instruction sentence may be, "Please determine whether the following comment by the poster is from the person involved in the news article." In response to such a prompt, the sentence generation model outputs a natural language response as a determination result.

[0052] The selection unit 44 selects an authenticated account related to the content when the determination unit 43 determines that the poster is a party. Based on the category of the news article that is the content, the selection unit 44 selects from the account information storage unit 32 an authenticated account that is an expert or specialist in the category.

[0053] For example, if the category of the news article is economics, the selection unit 44 selects an expert or a specialist in the economics category. In this case, the selection unit 44 selects a plurality of authenticated accounts.

[0054] The selection unit 44 may also select an authenticated account on the condition that the account has posted a news article or comment within the last three months.

[0055] The inquiry unit 45 inquires of the authenticated accounts selected by the selection unit 44 as to whether the poster is the person involved. Specifically, the selection unit 44 sends the news article, comment content, account information, etc. to the authenticated accounts selected by the selection unit 44, and inquires as to whether the poster is the person involved. Then, upon acquiring the results of the inquiries from each authenticated account, the inquiry unit 45 passes the results to the determination unit 46.

[0056] The determination unit 46 determines whether to make the comment public or private, depending on the result of the inquiry by the inquiry unit 45. For example, the determination unit 46 determines whether to make the comment public or private by utilizing a sentence generation model.

[0057] The determination unit 46 generates a prompt that includes the answer acquired from each authenticated account and an instruction sentence for determining whether the poster is the person in question. An example of the prompt will now be described with reference to Fig. 5. Fig. 5 is a schematic diagram of a prompt according to the embodiment.

[0058] As shown in Figure 5, the prompts include, for example, answers and instruction prompts (instruction sentences) obtained from each authenticated account. In the example shown in the figure, each answer includes the result of the determination as to whether or not the person is the person in question and the reason for that determination, and the instruction prompt is a sentence such as "Please determine from these answers whether A's account is A's."

[0059] The determination unit 46 inputs these prompts into the sentence generation model and obtains an answer to the prompt from the sentence generation model. At this time, if the determination unit 46 determines that the poster is the person involved based on the answer from the sentence generation model, the determination unit 46 decides to make the comment public. Furthermore, if the information processing device 1 determines that the poster is not the person involved based on the answer from the sentence generation model, that is, if it determines that the poster is likely to be an impersonator, the determination unit 46 decides to make the comment private. Note that the determination unit 46 may also decide to make the comment private when it cannot determine whether the poster is the person involved based on the answer from the sentence generation model.

[0060] Comments that are determined by the decision unit 46 to be posted by the person concerned are distributed as distribution content together with the news article, while comments that are determined to be posted by someone other than the person concerned are kept private. In other words, if it is determined that the person posting the comment is not the person concerned, that is, an impersonator, the comment will remain private. This makes it possible to prevent comments posted by impersonators, thereby improving the health of the comment section.

[0061] [3. Processing flow] Next, a processing procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of information processing according to the embodiment.

[0062] 6, first, the information processing device 1 accepts a comment on content (step S101), and then determines whether the posted comment is subject to determination of impersonation (step S102).

[0063] If the information processing device 1 determines that the device is not a target for spoofing check (step S102: No), it ends the process, and if it determines that the device is a target for spoofing check (step S102: Yes), it proceeds to the process of step S103.

[0064] Next, the information processing device 1 selects an authenticated account to which the inquiry will be sent (step S103), and sends an inquiry to the selected authenticated account (step S104). Next, the information processing device 1 obtains a response to the inquiry from the authenticated account (step S105).

[0065] Then, the information processing device 1 determines whether to make the comment public or private (step S106), and ends the process.

[0066] [4. Modifications] In the above embodiment, the content is a news article, but the present invention is not limited to this. The content may be a comment posted on a social networking site or the like.

[0067] [5. Effects] The information processing device 1 according to the embodiment described above includes a determination unit 43 that determines whether the poster of a comment on content is a party to the content based on the poster's account information, a selection unit 44 that selects an authenticated account associated with the content when the determination unit 43 determines that the poster is a party to the content, and an inquiry unit 45 that inquires of the authenticated account selected by the selection unit 44 whether the poster is the party to the content.

[0068] The selection unit 44 selects a plurality of authenticated accounts, and the inquiry unit 45 makes an inquiry to the plurality of authenticated accounts. The information processing device 1 also includes a decision unit 46 that decides whether to make a statement public or private based on the result of the inquiry by the inquiry unit 45.

[0069] In addition, the determination unit 46 generates a prompt that includes the result of an inquiry to the authenticated account and an instruction sentence that determines whether the poster is the person in question, and determines whether to make the comment public or private based on the answer result obtained by inputting the prompt into the sentence generation model.

[0070] The selection unit 44 also selects authenticated accounts of experts who belong to the genre of the news article that will be the content. The selection unit 44 also selects authenticated accounts of users who have posted the news article that will be the content or comments on the news article within a certain period of time.

[0071] By performing any one or a combination of the above-described processes, the information processing device according to the present application can improve the health of the comment section.

[0072] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 7. Fig. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 1 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0073] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0074] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0075] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 7, the output devices and input devices are collectively referred to as "input / output devices") via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0076] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0077] For example, when the computer 1000 functions as the information processing device 1 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0078] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0079] [7. Other] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0080] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0081] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0082] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0083] 1. Information processing equipment 2. Communications Department 3 Storage section 4. Control Unit 31 Content information storage unit 32 Account information storage unit 33 Sentence generation model memory section 41 Distribution Department 42 Reception Department 43 Judgment section 44 Selection section 45 Inquiry Department 46 Decision Section 50 User Terminals

Claims

1. a determination unit that determines whether a poster of a comment on content is a party to the content based on account information of the poster; a selection unit that selects an authenticated account associated with the content when the determination unit determines that the poster is the party; an inquiry unit that inquires of the authenticated account selected by the selection unit whether the poster is the person in question; An information processing device comprising:

2. The selection unit Selecting a plurality of said authenticated accounts; The inquiry unit conducting said inquiry to a plurality of said authenticated accounts; 2. The information processing device according to claim 1,

3. a decision unit that decides whether to make the comment public or private in accordance with the result of the inquiry by the inquiry unit; 2. The information processing apparatus according to claim 1, further comprising:

4. The determination unit Generate a prompt including an inquiry result to the authenticated account and an instruction sentence for determining whether the poster is the person in question, and input the prompt into a sentence generation model to obtain an answer, and then decide whether to make the comment public or private based on the answer result.

4. The information processing device according to claim 3,

5. The selection unit Selecting the authenticated accounts of experts who belong to the genre of the news articles that will be the content.

2. The information processing device according to claim 1,

6. The selection unit Selecting the authenticated accounts of users who have posted news articles or comments on news articles that constitute the content within a certain period of time.

2. The information processing device according to claim 1,

7. 1. A computer-implemented information processing method, comprising: a determining step of determining whether a poster of a comment on content is a party to the content based on account information of the poster; a selection step of selecting an authenticated account associated with the content when the determination step determines that the poster is the party; an inquiry step of inquiring about whether the poster is the person in question, from the authenticated account selected by the selection step; An information processing method comprising:

8. a determination step of determining whether a poster of a comment on content is a party to the content based on account information of the poster; a selection step of selecting an authenticated account associated with the content if the determination step determines that the poster is the party; an inquiry step of inquiring about whether the poster is the person in question, from the authenticated account selected by the selection step; An information processing program characterized by causing a computer to execute the above.

Images